main : disable token count by default (ggml-org#4874)

Author: ggerganov

common/common.cpp

@@ -630,7 +630,7 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
                 break;
             }
             params.ppl_stride = std::stoi(argv[i]);
-        } else if (arg == "-stc" || arg == "--show_token_count") {
+        } else if (arg == "-stc" || arg == "--show-token-count") {
             if (++i >= argc) {
                 invalid_param = true;
                 break;
@@ -950,8 +950,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  --override-kv KEY=TYPE:VALUE\n");
     printf("                        advanced option to override model metadata by key. may be specified multiple times.\n");
     printf("                        types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
-    printf("  -stc N --show_token_count N\n");
-    printf("                        show consumed tokens every N tokens\n");
+    printf("  -stc N --show-token-count N\n");
+    printf("                        show consumed tokens every N tokens (default: %d)\n", params.token_interval);
     printf("\n");
 #ifndef LOG_DISABLE_LOGS
     log_print_usage();

common/common.h

@@ -64,7 +64,7 @@ struct gpt_params {
     int32_t n_beams                         = 0;     // if non-zero then use beam search of given width.
     int32_t grp_attn_n                      = 1;     // group-attention factor
     int32_t grp_attn_w                      = 512;   // group-attention width
-    int32_t token_interval                  = 512;   // show token count every 512 tokens
+    int32_t token_interval                  = -1;    // show token count every 512 tokens (-1 = disabled)
     float   rope_freq_base                  = 0.0f;  // RoPE base frequency
     float   rope_freq_scale                 = 0.0f;  // RoPE frequency scaling factor
     float   yarn_ext_factor                 = -1.0f; // YaRN extrapolation mix factor

examples/main/main.cpp

@@ -651,8 +651,8 @@ int main(int argc, char ** argv) {
 
                 LOG("n_past = %d\n", n_past);
                 // Display total tokens alongside total time
-                if (n_past % params.token_interval == 0) {
-                    printf("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx);
+                if (params.token_interval > 0 && n_past % params.token_interval == 0) {
+                    LOG_TEE("\n\033[31mTokens consumed so far = %d / %d \033[0m\n", n_past, n_ctx);
                 }
             }